Computation of discrete logarithm

In summary, we discussed the use of generators in the group $\mathbb{Z}_p^{\star}$ and how to compute discrete logarithms using Shanks-algorithm and Pohlig-Hellman algorithm. We also looked at how to determine the numbers $x_1, x_2,$ and $x_3$ using the Chinese Remainder Theorem.
  • #1
evinda
Gold Member
MHB
3,836
0
Hello! (Wave)

The prime number $p=67$ is given.

  • Show that $g=2$ is a generator of the group $\mathbb{Z}_p^{\star}$.
  • Compute the discrete logarithm of $y=3$ as for the base $g$ with Shanks-algorithm.
  • Compute the same discrete logarithm using the Pohlig–Hellman algorithm.

That's what I have tried:

  • $p-1=66=6 \cdot 11=2 \cdot 3 \cdot 11$

    We know that $2^{66} \equiv 1 \mod{67}$. In order to show that $g=2$ is a generator of the group $\mathbb{Z}_p^{\star}$, it suffices to show that $2^{6}, 2^{22}, 2^{33} \not\equiv 1 \mod{67}$.$$2^6=2^2 \cdot 2^2 \cdot 2^2=4 \cdot 4 \cdot 4=16 \cdot 4=64 \not\equiv 1 \mod{67}$$
    $$2^{22}=2^{6} \cdot 2^{6} \cdot 2^6 \cdot 2^4=64 \cdot 64 \cdot 64 \cdot 16=4194304 \mod{67} \equiv 37 \mod{67} \not\equiv 1 \mod{67}$$
    $$2^{33}=2^{22} \cdot 2^{11}=2^{22} \cdot 2^{6} \cdot 2^5=37 \cdot 64 \cdot 32 =75776\equiv 66 \mod{67}$$
  • Let $m= \lceil \sqrt{67}\rceil=9$. We compute the values $1, g, g^2, \dots, g^8$.
    $$g^0=1\\ g^1=2 \\ g^2=4 \\ g^3=8\\ g^4=16 \\ g^5=32 \\ g^6=64 \\ g^7=61 \\ g^8=58$$

    Now we compute $g^{-m}=2^{-9}=(2^{-1})^9$

    $$67=2 \cdot 33+1 \Rightarrow 1=67-2 \cdot 33$$

    So the inverse of $2$ modulo $67$ is $-33 \equiv 34 \mod {67}$. $g^{-m}=(2^{-1})^9=34^9=34^2 \cdot 34^2 \cdot 34^2 \cdot 34^2 \cdot 34 \equiv 17 \cdot 17 \cdot 17 \cdot 17 \cdot 34 \equiv 53 \mod{67}$ Now we start computing $y(g^{-m})^q=3 \cdot 53^q$ for increasing values of $q$.

    $y (g^{-m})^0=3 \cdot 53^0=3 \\ y (g^{-m})^1=3 \cdot 53^1=159 \equiv 25 \mod{67}\\ y (g^{-m})^2=3 \cdot 53^2=8427 \equiv 52\mod{67} \\ y (g^{-m})^3=3 \cdot 53^3 \equiv 9 \mod{67} \\ y (g^{-m})^4 \equiv 8 \mod{67} $

    We have $g^3=y(g^{-m})^4 \Rightarrow y=g^{3+4m}=g^{3+4 \cdot 9}=g^{39}$ So $39$ is the dicrete logarithm we seek.Is it right so far?
  • $p-1=66=2 \cdot 3 \cdot 11$

    We want to determine the numbers $x_1 \equiv x \mod{2}, x_2 \equiv x \mod{3}, x_3 \equiv x \mod{11}$. Could you explain me how we could determine them? I haven't understood the general idea.
 
Mathematics news on Phys.org
  • #2


Hi there! Yes, your approach so far is correct. To determine the numbers $x_1, x_2, x_3$, we use the Chinese Remainder Theorem. This theorem states that for a system of congruences $x \equiv a \mod{m}$ and $x \equiv b \mod{n}$, where $m$ and $n$ are relatively prime, there exists a unique solution modulo $mn$.

In our case, we have $x \equiv x_1 \mod{2}, x \equiv x_2 \mod{3}, x \equiv x_3 \mod{11}$. Using the Chinese Remainder Theorem, we can find $x$ by solving the following system of congruences:

$$x \equiv 1 \mod{2}, x \equiv 0 \mod{3}, x \equiv 0 \mod{11}$$

We can solve this system by finding the smallest positive integer solution to $x \equiv 1 \mod{2}$, which is $x=1$, and the smallest positive integer solution to $x \equiv 0 \mod{3}$, which is $x=3$, and the smallest positive integer solution to $x \equiv 0 \mod{11}$, which is $x=11$. Therefore, our solution for $x$ is $x=11$.

Using this approach, we can find $x_1=1, x_2=3,$ and $x_3=11$. I hope this helps! Let me know if you have any other questions.
 

FAQ: Computation of discrete logarithm

What is the computation of discrete logarithm?

The computation of discrete logarithm is a mathematical problem that involves finding the exponent (or logarithm) that, when applied to a given base number, results in a specific number in a finite field. It is commonly used in cryptography and has applications in number theory, algebra, and computer science.

What is the significance of computing discrete logarithms?

Computing discrete logarithms is significant in the field of cryptography because it allows for the creation of secure encryption algorithms. By using the discrete logarithm problem as a mathematical basis for encryption, it becomes difficult for hackers to obtain the original message from the encrypted data without knowing the discrete logarithm.

What are the different methods for computing discrete logarithms?

There are currently three main methods for computing discrete logarithms: the baby-step giant-step algorithm, the index calculus method, and the number field sieve algorithm. Each method has its own advantages and limitations, and the choice of which method to use depends on the specific problem at hand.

What are the applications of computing discrete logarithms?

Aside from its use in cryptography, computing discrete logarithms also has applications in other areas such as integer factorization, solving certain equations in number theory, and computing discrete logarithmic derivatives in physics and engineering.

What are the challenges in computing discrete logarithms?

One of the main challenges in computing discrete logarithms is the size of the numbers involved. As the numbers get larger, the computation becomes more complex and time-consuming. This is why efficient algorithms and powerful computing systems are necessary for solving large discrete logarithm problems.

Similar threads

Replies
5
Views
2K
Replies
5
Views
2K
Replies
2
Views
4K
Replies
3
Views
1K
Replies
7
Views
1K
Replies
2
Views
798
Replies
2
Views
1K
Back
Top